A new study, which will be published in the American Journal of Psychiatry, suggests researchers from the University of Amsterdam have developed in an AI algorithm that can accurately predict within a week whether or not the common antidepressant Sertraline (better known as Zoloft) will work.
According to Neuroscience News, “the algorithm focuses on blood flow in the anterior cingulate cortex and symptom severity.”
This is really good news.
Currently, it can take 6-8 weeks to really know if something is working, so this slices that number dramatically, and can help speed up the time-consuming “trial and error” approach to prescribing the right antidepressant.
The current 6-8 week waiting period not only comes with more side effects, but also raises the risk of a patient abandoning treatment.
It’s a common tale.
For example, I was completely jaded by the time doctors finally found an antidepressant that worked for me.
In fact, I’d tried four and none of them had made the slightest difference. Yet, I kept giving it a shot and shockingly, that 5th antidepressant did the trick.
It didn’t cure me by any means (as I still struggle with intense bouts), but about three weeks in, I suddenly realized, “Hey I haven’t been that depressed in a few weeks.” I was skeptical it was the antidepressant, but yeah, as time passed, it soon became apparent to both myself and everyone around me — this thing was working.
I was extraordinarily surprised, relieved and blessed.
I’ve known so many who’ve very, very reluctantly tried an antidepressant, and when that particular one doesn’t work, they just give up on the whole process.
“I knew antidepressants wouldn’t work. No way I’m trying another one of those for two months.”
Of course, that’s anyone’s right. But my journey showed just how much time and trial-and-error there can be to this thing.
And many have similar stories.
So this study has big implications.
Now, caveat, it did only focus on one particular antidepressant (but a common one, in the very common SSRI class), but hopefully AI algorithms for other medicines can be developed.
My hunch is that a) more reluctant people who need them will give them a try and b) they’ll be more likely to keep trying if they can quickly measure whether it’s working.
Anything that helps doctors identify the correct treatment faster is a potential game-changer for getting people the help they need.
More on the specifics of the study, via Neuroscience News.
In a previous study conducted in the United States, MRI scans and clinical data were administered to 229 patients with major depression before and after a week of treatment with sertraline or placebo.
The Amsterdam researchers then developed and applied an algorithm to this data to investigate whether they could predict the treatment response to sertraline.
“The algorithm suggested that blood flow in the anterior cingulate cortex, the area of brain involved in emotion regulation, would be predictive of the efficacy of the drug. And at the second measurement, a week after the start, the severity of their symptoms turned out to be additionally predictive” says Eric Ruhé, psychiatrist at Radboudumc.
So, thank God.
Btw, my continual disclaimer: this doesn’t mean an antidepressant is right for you. It helped me a lot. But I still struggle often, and you’re not me, and many don’t respond to treatment, while others have their lives changed for the better.
It’s a decision for you to make and discuss with your doctor.
And on that topic…
For readers from the United States….
Find a psychiatrist here.
Find a therapist here.
For readers, internationally, please seek help from a local resource.
If you’re having thoughts of harming yourself or others, please call the National Suicide Lifeline at 1-800-273-8255.
[Photo: Via Pexels, by Polina Tankilevitch]
